Prosper Loan Data
Univariate Plots Section
## [1] "ListingKey"
## [2] "ListingNumber"
## [3] "ListingCreationDate"
## [4] "CreditGrade"
## [5] "Term"
## [6] "LoanStatus"
## [7] "ClosedDate"
## [8] "BorrowerAPR"
## [9] "BorrowerRate"
## [10] "LenderYield"
## [11] "EstimatedEffectiveYield"
## [12] "EstimatedLoss"
## [13] "EstimatedReturn"
## [14] "ProsperRating..numeric."
## [15] "ProsperRating..Alpha."
## [16] "ProsperScore"
## [17] "ListingCategory..numeric."
## [18] "BorrowerState"
## [19] "Occupation"
## [20] "EmploymentStatus"
## [21] "EmploymentStatusDuration"
## [22] "IsBorrowerHomeowner"
## [23] "CurrentlyInGroup"
## [24] "GroupKey"
## [25] "DateCreditPulled"
## [26] "CreditScoreRangeLower"
## [27] "CreditScoreRangeUpper"
## [28] "FirstRecordedCreditLine"
## [29] "CurrentCreditLines"
## [30] "OpenCreditLines"
## [31] "TotalCreditLinespast7years"
## [32] "OpenRevolvingAccounts"
## [33] "OpenRevolvingMonthlyPayment"
## [34] "InquiriesLast6Months"
## [35] "TotalInquiries"
## [36] "CurrentDelinquencies"
## [37] "AmountDelinquent"
## [38] "DelinquenciesLast7Years"
## [39] "PublicRecordsLast10Years"
## [40] "PublicRecordsLast12Months"
## [41] "RevolvingCreditBalance"
## [42] "BankcardUtilization"
## [43] "AvailableBankcardCredit"
## [44] "TotalTrades"
## [45] "TradesNeverDelinquent..percentage."
## [46] "TradesOpenedLast6Months"
## [47] "DebtToIncomeRatio"
## [48] "IncomeRange"
## [49] "IncomeVerifiable"
## [50] "StatedMonthlyIncome"
## [51] "LoanKey"
## [52] "TotalProsperLoans"
## [53] "TotalProsperPaymentsBilled"
## [54] "OnTimeProsperPayments"
## [55] "ProsperPaymentsLessThanOneMonthLate"
## [56] "ProsperPaymentsOneMonthPlusLate"
## [57] "ProsperPrincipalBorrowed"
## [58] "ProsperPrincipalOutstanding"
## [59] "ScorexChangeAtTimeOfListing"
## [60] "LoanCurrentDaysDelinquent"
## [61] "LoanFirstDefaultedCycleNumber"
## [62] "LoanMonthsSinceOrigination"
## [63] "LoanNumber"
## [64] "LoanOriginalAmount"
## [65] "LoanOriginationDate"
## [66] "LoanOriginationQuarter"
## [67] "MemberKey"
## [68] "MonthlyLoanPayment"
## [69] "LP_CustomerPayments"
## [70] "LP_CustomerPrincipalPayments"
## [71] "LP_InterestandFees"
## [72] "LP_ServiceFees"
## [73] "LP_CollectionFees"
## [74] "LP_GrossPrincipalLoss"
## [75] "LP_NetPrincipalLoss"
## [76] "LP_NonPrincipalRecoverypayments"
## [77] "PercentFunded"
## [78] "Recommendations"
## [79] "InvestmentFromFriendsCount"
## [80] "InvestmentFromFriendsAmount"
## [81] "Investors"## ListingKey ListingNumber ListingCreationDate
## 17A93590655669644DB4C06: 6 Min. : 4 02:03.5: 12
## 349D3587495831350F0F648: 4 1st Qu.: 400919 20:28.5: 12
## 47C1359638497431975670B: 4 Median : 600554 22:05.3: 12
## 8474358854651984137201C: 4 Mean : 627886 29:50.4: 12
## DE8535960513435199406CE: 4 3rd Qu.: 892634 00:34.6: 11
## 04C13599434217079754AEE: 3 Max. :1255725 04:49.3: 11
## (Other) :113912 (Other):113867
## CreditGrade Term LoanStatus
## :84984 Min. :12.00 Current :56576
## C : 5649 1st Qu.:36.00 Completed :38074
## D : 5153 Median :36.00 Chargedoff :11992
## B : 4389 Mean :40.83 Defaulted : 5018
## AA : 3509 3rd Qu.:36.00 Past Due (1-15 days) : 806
## HR : 3508 Max. :60.00 Past Due (31-60 days): 363
## (Other): 6745 (Other) : 1108
## ClosedDate BorrowerAPR BorrowerRate
## :58848 Min. :0.00653 Min. :0.0000
## 3/4/14 0:00 : 105 1st Qu.:0.15629 1st Qu.:0.1340
## 2/19/14 0:00 : 100 Median :0.20976 Median :0.1840
## 2/11/14 0:00 : 92 Mean :0.21883 Mean :0.1928
## 10/30/12 0:00: 81 3rd Qu.:0.28381 3rd Qu.:0.2500
## 2/26/13 0:00 : 78 Max. :0.51229 Max. :0.4975
## (Other) :54633 NA's :25
## LenderYield EstimatedEffectiveYield EstimatedLoss
## Min. :-0.0100 Min. :-0.183 Min. :0.005
## 1st Qu.: 0.1242 1st Qu.: 0.116 1st Qu.:0.042
## Median : 0.1730 Median : 0.162 Median :0.072
## Mean : 0.1827 Mean : 0.169 Mean :0.080
## 3rd Qu.: 0.2400 3rd Qu.: 0.224 3rd Qu.:0.112
## Max. : 0.4925 Max. : 0.320 Max. :0.366
## NA's :29084 NA's :29084
## EstimatedReturn ProsperRating..numeric. ProsperRating..Alpha.
## Min. :-0.183 Min. :1.000 :29084
## 1st Qu.: 0.074 1st Qu.:3.000 C :18345
## Median : 0.092 Median :4.000 B :15581
## Mean : 0.096 Mean :4.072 A :14551
## 3rd Qu.: 0.117 3rd Qu.:5.000 D :14274
## Max. : 0.284 Max. :7.000 E : 9795
## NA's :29084 NA's :29084 (Other):12307
## ProsperScore ListingCategory..numeric. BorrowerState
## Min. : 1.00 Min. : 0.000 CA :14717
## 1st Qu.: 4.00 1st Qu.: 1.000 TX : 6842
## Median : 6.00 Median : 1.000 NY : 6729
## Mean : 5.95 Mean : 2.774 FL : 6720
## 3rd Qu.: 8.00 3rd Qu.: 3.000 IL : 5921
## Max. :11.00 Max. :20.000 : 5515
## NA's :29084 (Other):67493
## Occupation EmploymentStatus
## Other :28617 Employed :67322
## Professional :13628 Full-time :26355
## Computer Programmer : 4478 Self-employed: 6134
## Executive : 4311 Not available: 5347
## Teacher : 3759 Other : 3806
## Administrative Assistant: 3688 : 2255
## (Other) :55456 (Other) : 2718
## EmploymentStatusDuration IsBorrowerHomeowner CurrentlyInGroup
## Min. : 0.00 Mode :logical Mode :logical
## 1st Qu.: 26.00 FALSE:56459 FALSE:101218
## Median : 67.00 TRUE :57478 TRUE :12719
## Mean : 96.07
## 3rd Qu.:137.00
## Max. :755.00
## NA's :7625
## GroupKey DateCreditPulled
## :100596 11/4/13 14:12: 8
## 783C3371218786870A73D20: 1140 07:54.9 : 6
## 3D4D3366260257624AB272D: 916 12/23/13 9:38: 6
## 6A3B336601725506917317E: 698 14:22.9 : 6
## FEF83377364176536637E50: 611 33:37.0 : 6
## C9643379247860156A00EC0: 342 34:47.1 : 6
## (Other) : 9634 (Other) :113899
## CreditScoreRangeLower CreditScoreRangeUpper FirstRecordedCreditLine
## Min. : 0.0 Min. : 19.0 : 697
## 1st Qu.:660.0 1st Qu.:679.0 12/1/93 0:00: 185
## Median :680.0 Median :699.0 11/1/94 0:00: 178
## Mean :685.6 Mean :704.6 11/1/95 0:00: 168
## 3rd Qu.:720.0 3rd Qu.:739.0 4/1/90 0:00 : 161
## Max. :880.0 Max. :899.0 3/1/95 0:00 : 159
## NA's :591 NA's :591 (Other) :112389
## CurrentCreditLines OpenCreditLines TotalCreditLinespast7years
## Min. : 0.00 Min. : 0.00 Min. : 2.00
## 1st Qu.: 7.00 1st Qu.: 6.00 1st Qu.: 17.00
## Median :10.00 Median : 9.00 Median : 25.00
## Mean :10.32 Mean : 9.26 Mean : 26.75
## 3rd Qu.:13.00 3rd Qu.:12.00 3rd Qu.: 35.00
## Max. :59.00 Max. :54.00 Max. :136.00
## NA's :7604 NA's :7604 NA's :697
## OpenRevolvingAccounts OpenRevolvingMonthlyPayment InquiriesLast6Months
## Min. : 0.00 Min. : 0.0 Min. : 0.000
## 1st Qu.: 4.00 1st Qu.: 114.0 1st Qu.: 0.000
## Median : 6.00 Median : 271.0 Median : 1.000
## Mean : 6.97 Mean : 398.3 Mean : 1.435
## 3rd Qu.: 9.00 3rd Qu.: 525.0 3rd Qu.: 2.000
## Max. :51.00 Max. :14985.0 Max. :105.000
## NA's :697
## TotalInquiries CurrentDelinquencies AmountDelinquent
## Min. : 0.000 Min. : 0.0000 Min. : 0.0
## 1st Qu.: 2.000 1st Qu.: 0.0000 1st Qu.: 0.0
## Median : 4.000 Median : 0.0000 Median : 0.0
## Mean : 5.584 Mean : 0.5921 Mean : 984.5
## 3rd Qu.: 7.000 3rd Qu.: 0.0000 3rd Qu.: 0.0
## Max. :379.000 Max. :83.0000 Max. :463881.0
## NA's :1159 NA's :697 NA's :7622
## DelinquenciesLast7Years PublicRecordsLast10Years
## Min. : 0.000 Min. : 0.0000
## 1st Qu.: 0.000 1st Qu.: 0.0000
## Median : 0.000 Median : 0.0000
## Mean : 4.155 Mean : 0.3126
## 3rd Qu.: 3.000 3rd Qu.: 0.0000
## Max. :99.000 Max. :38.0000
## NA's :990 NA's :697
## PublicRecordsLast12Months RevolvingCreditBalance BankcardUtilization
## Min. : 0.000 Min. : 0 Min. :0.000
## 1st Qu.: 0.000 1st Qu.: 3121 1st Qu.:0.310
## Median : 0.000 Median : 8549 Median :0.600
## Mean : 0.015 Mean : 17599 Mean :0.561
## 3rd Qu.: 0.000 3rd Qu.: 19521 3rd Qu.:0.840
## Max. :20.000 Max. :1435667 Max. :5.950
## NA's :7604 NA's :7604 NA's :7604
## AvailableBankcardCredit TotalTrades
## Min. : 0 Min. : 0.00
## 1st Qu.: 880 1st Qu.: 15.00
## Median : 4100 Median : 22.00
## Mean : 11210 Mean : 23.23
## 3rd Qu.: 13180 3rd Qu.: 30.00
## Max. :646285 Max. :126.00
## NA's :7544 NA's :7544
## TradesNeverDelinquent..percentage. TradesOpenedLast6Months
## Min. :0.000 Min. : 0.000
## 1st Qu.:0.820 1st Qu.: 0.000
## Median :0.940 Median : 0.000
## Mean :0.886 Mean : 0.802
## 3rd Qu.:1.000 3rd Qu.: 1.000
## Max. :1.000 Max. :20.000
## NA's :7544 NA's :7544
## DebtToIncomeRatio IncomeRange IncomeVerifiable
## Min. : 0.000 $25,000-49,999:32192 Mode :logical
## 1st Qu.: 0.140 $50,000-74,999:31050 FALSE:8669
## Median : 0.220 $100,000+ :17337 TRUE :105268
## Mean : 0.276 $75,000-99,999:16916
## 3rd Qu.: 0.320 Not displayed : 7741
## Max. :10.010 $1-24,999 : 7274
## NA's :8554 (Other) : 1427
## StatedMonthlyIncome LoanKey TotalProsperLoans
## Min. : 0 CB1B37030986463208432A1: 6 Min. :0.00
## 1st Qu.: 3200 2DEE3698211017519D7333F: 4 1st Qu.:1.00
## Median : 4667 9F4B37043517554537C364C: 4 Median :1.00
## Mean : 5608 D895370150591392337ED6D: 4 Mean :1.42
## 3rd Qu.: 6825 E6FB37073953690388BC56D: 4 3rd Qu.:2.00
## Max. :1750003 0D8F37036734373301ED419: 3 Max. :8.00
## (Other) :113912 NA's :91852
## TotalProsperPaymentsBilled OnTimeProsperPayments
## Min. : 0.00 Min. : 0.00
## 1st Qu.: 9.00 1st Qu.: 9.00
## Median : 16.00 Median : 15.00
## Mean : 22.93 Mean : 22.27
## 3rd Qu.: 33.00 3rd Qu.: 32.00
## Max. :141.00 Max. :141.00
## NA's :91852 NA's :91852
## ProsperPaymentsLessThanOneMonthLate ProsperPaymentsOneMonthPlusLate
## Min. : 0.00 Min. : 0.00
## 1st Qu.: 0.00 1st Qu.: 0.00
## Median : 0.00 Median : 0.00
## Mean : 0.61 Mean : 0.05
## 3rd Qu.: 0.00 3rd Qu.: 0.00
## Max. :42.00 Max. :21.00
## NA's :91852 NA's :91852
## ProsperPrincipalBorrowed ProsperPrincipalOutstanding
## Min. : 0 Min. : 0
## 1st Qu.: 3500 1st Qu.: 0
## Median : 6000 Median : 1627
## Mean : 8472 Mean : 2930
## 3rd Qu.:11000 3rd Qu.: 4127
## Max. :72499 Max. :23451
## NA's :91852 NA's :91852
## ScorexChangeAtTimeOfListing LoanCurrentDaysDelinquent
## Min. :-209.00 Min. : 0.0
## 1st Qu.: -35.00 1st Qu.: 0.0
## Median : -3.00 Median : 0.0
## Mean : -3.22 Mean : 152.8
## 3rd Qu.: 25.00 3rd Qu.: 0.0
## Max. : 286.00 Max. :2704.0
## NA's :95009
## LoanFirstDefaultedCycleNumber LoanMonthsSinceOrigination LoanNumber
## Min. : 0.00 Min. : 0.0 Min. : 1
## 1st Qu.: 9.00 1st Qu.: 6.0 1st Qu.: 37332
## Median :14.00 Median : 21.0 Median : 68599
## Mean :16.27 Mean : 31.9 Mean : 69444
## 3rd Qu.:22.00 3rd Qu.: 65.0 3rd Qu.:101901
## Max. :44.00 Max. :100.0 Max. :136486
## NA's :96985
## LoanOriginalAmount LoanOriginationDate LoanOriginationQuarter
## Min. : 1000 1/22/14 0:00 : 491 Q4 2013:14450
## 1st Qu.: 4000 11/13/13 0:00: 490 Q1 2014:12172
## Median : 6500 2/19/14 0:00 : 439 Q3 2013: 9180
## Mean : 8337 10/16/13 0:00: 434 Q2 2013: 7099
## 3rd Qu.:12000 1/28/14 0:00 : 339 Q3 2012: 5632
## Max. :35000 9/24/13 0:00 : 316 Q2 2012: 5061
## (Other) :111428 (Other):60343
## MemberKey MonthlyLoanPayment LP_CustomerPayments
## 63CA34120866140639431C9: 9 Min. : 0.0 Min. : -2.35
## 16083364744933457E57FB9: 8 1st Qu.: 131.6 1st Qu.: 1005.76
## 3A2F3380477699707C81385: 8 Median : 217.7 Median : 2583.83
## 4D9C3403302047712AD0CDD: 8 Mean : 272.5 Mean : 4183.08
## 739C338135235294782AE75: 8 3rd Qu.: 371.6 3rd Qu.: 5548.40
## 7E1733653050264822FAA3D: 8 Max. :2251.5 Max. :40702.39
## (Other) :113888
## LP_CustomerPrincipalPayments LP_InterestandFees LP_ServiceFees
## Min. : 0.0 Min. : -2.35 Min. :-664.87
## 1st Qu.: 500.9 1st Qu.: 274.87 1st Qu.: -73.18
## Median : 1587.5 Median : 700.84 Median : -34.44
## Mean : 3105.5 Mean : 1077.54 Mean : -54.73
## 3rd Qu.: 4000.0 3rd Qu.: 1458.54 3rd Qu.: -13.92
## Max. :35000.0 Max. :15617.03 Max. : 32.06
##
## LP_CollectionFees LP_GrossPrincipalLoss LP_NetPrincipalLoss
## Min. :-9274.75 Min. : -94.2 Min. : -954.5
## 1st Qu.: 0.00 1st Qu.: 0.0 1st Qu.: 0.0
## Median : 0.00 Median : 0.0 Median : 0.0
## Mean : -14.24 Mean : 700.4 Mean : 681.4
## 3rd Qu.: 0.00 3rd Qu.: 0.0 3rd Qu.: 0.0
## Max. : 0.00 Max. :25000.0 Max. :25000.0
##
## LP_NonPrincipalRecoverypayments PercentFunded Recommendations
## Min. : 0.00 Min. :0.7000 Min. : 0.00000
## 1st Qu.: 0.00 1st Qu.:1.0000 1st Qu.: 0.00000
## Median : 0.00 Median :1.0000 Median : 0.00000
## Mean : 25.14 Mean :0.9986 Mean : 0.04803
## 3rd Qu.: 0.00 3rd Qu.:1.0000 3rd Qu.: 0.00000
## Max. :21117.90 Max. :1.0125 Max. :39.00000
##
## InvestmentFromFriendsCount InvestmentFromFriendsAmount Investors
## Min. : 0.00000 Min. : 0.00 Min. : 1.00
## 1st Qu.: 0.00000 1st Qu.: 0.00 1st Qu.: 2.00
## Median : 0.00000 Median : 0.00 Median : 44.00
## Mean : 0.02346 Mean : 16.55 Mean : 80.48
## 3rd Qu.: 0.00000 3rd Qu.: 0.00 3rd Qu.: 115.00
## Max. :33.00000 Max. :25000.00 Max. :1189.00
## This data set contains 113,937 loans with 81 variables on each loan, including loan amount, borrower rate (or interest rate), current loan status, borrower income, borrower employment status, borrower credit history, and the latest payment information.
Plotting Borrower Rate histogram reveals that most of Prosper borrowers have their loans’ rate (APR) of around 14%.
Only 3 types of loan terms offered by Prosper: 12, 36 and 60 months. As we can see from the chart above, most of the borrowers select 36 months term. More than 75% borrowers prefer 36 months or 3 years terms, probably because it gives enough length to repay the loan but not too long to accumulate unnecessary interests.
The plot above illustrates the lower range of borrowers’ credit scores. It follows normal curve distribution. Most borrowers’ credit scores fall in around 670 and 680. Credit score in this range is considered from Fair to Good.
It is not surprising that the majority of the borrowers have regular income from employment. However, the data have ambiguity since employed category can be further divided into part-time and full-time, and these two sub-categories also exist as options.
The first Revolving Credit Balance plot indicates positive skew distribution. The Mean is higher than the Median as it is “pulled” to the right. Because the plot is a long tailed one, it is transformed to log10 to better understand the distribution of the data. As we can see from the log the count peaks at around 0 (no revolving balance) and gradually decreases as the revolving balance increases. However, there is no significant difference in the distributions shown by log10, thus it is confirmed that the plot has postive skew distribution.
Similar to Revolving Credit Balance, Monthly Loan Payment plot also follows positive skew distribution with Mean value is higher than the Median. Most borrowers have monthly loan payment around $150.
Debt to Income Ratio plot also has positive skew distribution in which majority of borrowers’ ratios are around 0.2.
Again, Current Credit Lines plot also shows positive skew distribution. While there are outliers data such as 59 (Max), most borrowers have around 8 credit lines.
ProsperRating..Alpha. plot follows normal distribution. The X axis shows the credit grades from AA, which is the highest credit grade and has the lowest probability of default, to HR, which is the lowest credit grade. HR credit grade also means that there is no credit history or history of defaults. Most debtors have C grade which right in the middle.
In this plot we are looking at how the borrowers are distributed based on their occupations. Unfortunately, by a huge margin, most of the records have “Other”. Prosper needs to improve the data entry to have more specific values. Moreover, the second highest occupation is Professional, which can also be broken down into more specific profession.
Most of Prosper’s debtors are in $25,000-49,999 income range. No one in the data has income greater than $100,000. There are records having “Not displayed”. The distribution of income range might change if values of each Not displayed record is known.
Univariate Analysis
What is the structure of your dataset?
There are 113,937 records in the dataset with 81 variables. Variables ProsperRating(Alpha) and IncomeRange are ordered factor variables with the following levels.
Highest to Lowest; ProsperRating(Alpha): “AA”,“A”,“B”,“C”,“D”,“E”,“HR” IncomeRange: “$100,000+”,“$75,000-99,999”,“$50,000-74,999”,“$25,000-49,999”,“$1-24,999”,“$0”.
What is/are the main feature(s) of interest in your dataset?
The main features of interest in this dataset are the BorrowerRate, CreditScoreRangeLower and DebtToIncomeRatio.
What other features in the dataset do you think will help support your
investigation into your feature(s) of interest?
EmploymentStatus, MonthlyLoanPayment and LoanStatus are the features that will be useful during investigation of the features of the interest.
Did you create any new variables from existing variables in the dataset?
I did not create any new vriables from the existing variables in the dataset since the existing ones are already self explanatory. Some of the existing variables even have very high correlation, for example BorrowerRate and BorrowerAPR, thus I only use one variable to represent the f.
Of the features you investigated, were there any unusual distributions?
Did you perform any operations on the data to tidy, adjust, or change the form
of the data? If so, why did you do this?
The Revolving Credit Balance plot is a very long tailed one. To see if there is a hidden distribution unseen, the plot is transforemed using log10. However, there is no significant difference in the distributions shown by log10, thus the original distribution which is positive skewed is confirmed.
Bivariate Plots Section
The boxplot above clearly indicates that Not Employed borrowers receive higher loan rate. This is not surprising considering the fact that not employed borrowers have higher risks. On the other hand, full-time and part-time employees have the lowest median loan rate among others.
##
## Pearson's product-moment correlation
##
## data: ld$CreditScoreRangeLower and ld$BorrowerRate
## t = -175.17, df = 113340, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.4661358 -0.4569730
## sample estimates:
## cor
## -0.4615667As the borrowers’ credit scores higher, the loan rates are lower. This is inline with the assumption that people with higher credit score tend to have lower risk in terms of loan default.
In the plot above the correlation between Debt to Income Ratio and Monthly Loan Payment is investigated. The plot is limited to max debt ratio = 1 since data with ratio greater than 1 is considered as outliers. Plot shows that from ratio 0.05 to 0.4, the monthly loan payment varies greatly.From 0.4 onward, the loan payment variations become more stable with slightly inclining trend.
Two boxplots above are created to investigate the correlation between Borrower rate, Credit Score and Borrower State. In the second plot, borrowers from Maine enjoy the lowest rate. Interestingly, the first plot shows that borrowers from Mane have one of the lowest credit score medians among other states. On the other hand, borrowers from North Dakota have the lowest credit score median and consequently receive one of the highest borrower rate medians.
The above boxplot is used to investigate the correlation between borrower rate and when the loan was originated. Q3 2010 - Q4 2011 is the period when the medians of the borrower rate at the highest level. Since Q3 2012 it continuously decline.
Monthly payment values increase as the borrowers credit scores increase gradually. However, at credit score around 825, the monthly payment decreases. One possibility is that the Prosper’s customers with credit score of 825 and above tend to have lower loan rate and/or borrow less money, bringing down the monthly payment.
As previously mentioned, there is assumption that borrowers with lower credit score carry higher risk of loan default. The LoanStatus boxplot above confirms this assumption. While there are no significant diferences between current and past due loans, defaulted loans indicates that they occur more on borrowers with lower range of credit scores.
Bivariate Analysis
Talk about some of the relationships you observed in this part of the
investigation. How did the feature(s) of interest vary with other features in
the dataset?
Borrower rate correlates with employment status and credit score. Borrowers who have full-time and part-time employment typically have the lowest loan rate. On the opposite, Prosper’s customers who are not employed receive the highest rate.
The loan rate is negatively correlates with the credit score. The higher a customer’s credit score, the lower the rate she or he gets.
The higher loan rates for the borrowers who have lower credit scores is based on the assumption that the lower credit scores indicate higher risk of the loans being defaulted. As we can see from the last bivariat plot, the median of the defaulted borrowers is significantly lower than other categories.
Did you observe any interesting relationships between the other features
(not the main feature(s) of interest)?
Loans originated from Q3 2010 to Q4 2011 carry highest loan rates in the dataset. However, there is no obvious seasonal pattern, thus we cannot conclude that there is correlation between borrower rate and origination quarter.
What was the strongest relationship you found?
Borrower rate correlates negatively with the credit score range.
Multivariate Plots Section
The scatter plot above may seem overplotted, hence we can also use ellipse to depict the operation.
There is no discernible pattern between the rate, credit score and loan status. Most of the loans are in current status and they scatter in all combinations of rate and credit score. One thing to notice is that there are very vew loans in past due status for borrowers having credit scores above 600.
There are two observations from the chart above: 1. Employed and Full-time borrowers dominate the employment status 2. Employed and Full-time borrowers are leaning toward the high end of credit score ranges; however their employment status and credit score don’t seem to be correlated with the loan rate.
Both of the plots show similar pattern. However, the chart on the left that is for non-homeowners is skinier than the one for the homeowners. We can see that borrower rate is not really affected by the homeowner status, given the same credit score. However, we can also see that homeowners has wider credit score, with majority are in 650-850 (as opposed to 600-800 of the non homeowners)
Regardless the income ranges, all plots look to have similar pattern. Majority of borrowers are in $25,000-49,999 and $50,000-74,999 ranges.Again, we don’t see strong correlation between income range and credit score to the borrower rate.
##
## Pearson's product-moment correlation
##
## data: ld$ProsperRating..numeric. and ld$BorrowerRate
## t = -917.37, df = 84851, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.9537172 -0.9524846
## sample estimates:
## cor
## -0.9531049##
## Call:
## lm(formula = ld$BorrowerRate ~ ld$ProsperRating..numeric.)
##
## Coefficients:
## (Intercept) ld$ProsperRating..numeric.
## 0.36914 -0.04251Customers with the highest Prosper rating (AA and A or 6 and 7 in numerical scale) have the lowest loan rate. Interestingly, the plot shows that even though the customers’ credit score vary, as long as they have the highest rating, they receive the lowest borrowing In this case Prosper rating is better predictor for borrower rate than the credit score alone. The Pearson R test between between numerical rating and borrower rate is -0.95. which is very strong.
Multivariate Analysis
Talk about some of the relationships you observed in this part of the
investigation. Were there features that strengthened each other in terms of
looking at your feature(s) of interest?
Low loan rate is strongly correlated with the customer’s credit rating assigned by Prosper. Credit score alone is not a determining factor for customers in getting the ideal rate.
Were there any interesting or surprising interactions between features?
Income range does not seem to affect the loan rate. Two different customers with same credit score, say 650, and one with $25,000 income whie the other has $100,000, they could get the same loan rate.
OPTIONAL: Did you create any models with your dataset? Discuss the
strengths and limitations of your model.
Yes. A linear model is created from ProsperRating..numeric and BorrowerRate variables. The strength of this model is that there is strong correlation between these 2 variables as illustrated by the high R value. On the other side, for new data points, ProsperRating..numeric values may not be assigned immediately as other raw variables, rendering the linear model less effective.
Final Plots and Summary
Plot One
Description One
The loan rate is shown as strongly correlated with the alphanumeric ProsperRating variable. AA is the highest rate, and HR is the lowest. What interesting with this plot is it shows that the loan rate for each rating is independent of the credit score and the rate depends almost exclusively on the rating. For example, a borrower with credit core of 700 and rating AA may be assigned loan rate between 6-9%. Borrowers with the same credit score but have A rating may have to accept higher rate between 9-14%.
Plot Two
Description Two
This plot illustrates that defaulted loans are more likely to occur on borrowers with lower credit scores.I choose this plot because it confirms the assumption that borrowers with lower credit scores have higher risks. On the other hand, the past due loans do not differ signficantly to the current ones, perhaps due to the fact that most of past due loans will go back to current once the borrower pay the owned payment and only small amount of past due loans actually become defaulted.
Plot Three
Description Three
The boxplot above clearly indicates that Not Employed borrowers receive higher loan rate. This is not surprising considering the fact that not employed borrowers have higher risks due to not having regular income. The higher rate is to compensate this higher risk. Other categories having higher borrower rates are Other and Not Available. I suspect these categories are result of Employment Status data are not filled or identified by some borrowers. As employment status is an important consideration when approving the loan, people with unidentified employment status have to settle with higher loan rate.
Reflection
Prosper loan dataset contains huge amount of variables in which I suspect is a consolidation from various sources of data. Some of the variables though are telling the same thing in slightly different way. Among all variables, I am mainly interested in borrower rate and what are the factors that have impacts on it.
While there is correlation between credit score and employment status to the borrower rate, the strongest ones are shown by the ProsperRating..numeric. and ProsperRating..aplha. variables. However, it is mot likely that Prosper derives ProsperRating from other variables by following certain formula, and then use the rating as the direction to assign certain loan rate to their customers.
Some limitations of this model includes the missing of critical variables such as prime interest rate from the dataset. The prime rate is the underlying index for most credit cards, home equity loans and lines of credit, auto loans, and personal loans and it varies over the time. The information regarding the prime rate will be useful when analyzing the loan rate based on the loan originations time.